MMNet icon indicating copy to clipboard operation
MMNet copied to clipboard

tf.contrib.slim evaluation

Open prnvjb opened this issue 5 years ago • 5 comments

authors, thanks for opensourcing your code. I would like to know why did you choose tf.contrib.slim instead of tf.layers or just tf.keras? I'm trying to reimplement your using tf.keras which could be more simpler for more expremintation with tf.eager_execution to debug easily? what are implecations I should take to use tf.keras? Thanks!!

prnvjb avatar May 23 '19 13:05 prnvjb

Our internal framework is still dependent on older TF versions. We're currently migrating to newer versions and plan to adopt appropriate coding style in the future, but for now, we decided that releasing our code was more important than waiting for the migration to complete.

shurain avatar May 27 '19 03:05 shurain

HI,I made a few modification,and it can run on windows now. But how to use the models I trained?

tony2278 avatar May 27 '19 05:05 tony2278

image

tony2278 avatar May 27 '19 07:05 tony2278

do u have a demo about how to use this models?thanks. my email: [email protected]

tony2278 avatar Jun 05 '19 02:06 tony2278

Hi @tony2278 @shurain I tried to train for MModel with 4872 images, but never finished for 4 days Please let me know valid training.

ilous12 avatar Jun 11 '19 05:06 ilous12